Deep Neural Operator Driven Real Time Inference for Nuclear Systems to Enable Digital Twin Solutions

arXiv:2308.07523v2 Announce Type: replace-cross
Abstract: This paper focuses on the feasibility of Deep Neural Operator (DeepONet) as a robust surrogate modeling method within the context of digital twin (DT) for nuclear energy systems. Through benchmarking and evaluation, this study showcases the generalizability and computational efficiency of DeepONet in solving a challenging particle transport problem. DeepONet also exhibits remarkable prediction accuracy and speed, outperforming traditional ML methods, making it a suitable algorithm for real-time DT inference. However, the application of DeepONet …

abstract arxiv benchmarking computational context cs.lg deeponet digital digital twin efficiency energy evaluation inference modeling nuclear nuclear energy paper robust solutions stat.co stat.ml study systems through twin type